Gaussian distribution models are widely used for characterizing and modeling noise in CMOS sensors. Although it provides simplicity and speeds needed in real-time applications, it is usually not a very good representation of dark current characteristics observed in real devices. The statistical distribution of CMOS sensor dark noise is typically right-skewed with a long tail, i.e. with more “hot” pixels than described in a normal distribution. Furthermore, the spatial distribution in real devices typically exhibit a 1/f-like power spectrum instead of a flat spectrum from a simple Gaussian distributions model. When simulating sensor images, for example generating images and videos for training and testing image processing algorithms, it is important to reproduce both characteristics accurately. We propose a simple convolution-type algorithm using seed images with a log-normal distribution and randomized kernels to more accurately reproduce both statistical and spatial distributions. The convolution formulation also enables relatively easy GPU acceleration to support real-time execution for driving simulation platforms.